Method to detect opportunistic mixed mode transportation virtual hubs based on mobility patterns
A system, method and computer program product to detect opportunistic mixed mode transportation virtual hubs are disclosed. The system may allow commuters to benefit from more relevant and contextual recommendations for “park and ride” commutes by algorithmically detecting opportunistic mixed mode transportation virtual hubs based on traffic conditions, parking capacity measures and mobility patterns of commuters.
1 . A computer implemented method to detect opportunistic mixed mode transportation virtual hubs, the method comprising:
identifying, from probe data, an area where an on-street parking capacity and/or an off-street parking capacity is full during week-days;
identifying whether observed mobility patterns of a vehicle parking in the area comprise commuter parking patterns;
Identifying, based on map data, a location of a public transportation stop within a predetermined range of the area;
determining, based on historical traffic data and real-time traffic data, whether an observed traffic congestion increases from a historical traffic congestion level for observed traffic from the public transportation stop to a city center;
determining whether a full on-street parking capacity and/or a full off-street parking capacity during the day negatively modifies a mobility pattern of a resident of the area; and
determining, based on at least one of the observed mobility pattern of the vehicle parking in the area, the observed traffic congestion and the mobility pattern of the resident of the area, a current virtual park and ride index, where the current virtual park and ride index comprises a likelihood of the vehicle parking at a current virtual park and ride hub;
updating a database with a recommended virtual park and ride hub based on the future virtual park and ride index, map data, the real-time traffic data, public transportation data; and
activating an autonomous vehicle control system in response to the recommended virtual park and ride hub.
2 . The method of claim 1 , further comprising determining, using a trained machine learning model based on the current virtual park and ride index and area map features, a future virtual park and ride index, where the future virtual park and ride index comprises a likelihood of the vehicle parking at a future virtual park and ride hub.
3 . The method of claim 2 , further comprising providing, to a user, a recommended virtual park and ride hub based on the future virtual park and ride index, map data, the real-time traffic data, public transportation data, user travel preferences and/or user mobility patterns.
4 . The method of claim 3 , further comprising providing, based on the recommended virtual park and ride hub, suggestions to: park the vehicle at a different public transportation stop to reduce traffic congestion; choose a different virtual park and ride route to reduce an impact on the mobility pattern of the resident of the area; and/or recommend car-pooling from a start area to the recommended virtual park and ride hub based on similar mobility patterns of other commuters.
5 . The method of claim 3 , further comprising suggesting a virtual electric vehicle charging point park and ride hub that allows electric vehicles to charge within a predetermined location from the public transportation stop.
6 . The method of claim 1 , where the commuter parking patterns are determined from video data collected by cameras positioned in the area.
7 . The method of claim 3 , where providing, to the user, the recommended virtual park and ride hub comprises providing, to the user, the recommended virtual park and ride hub on a visual display.
8 . A system to detect opportunistic mixed mode transportation virtual hubs, comprising:
at least one memory configured to store computer executable instructions; and
at least one processor configured to execute the computer executable instructions to:
identify, from probe data, an area where an on-street parking capacity and/or an off-street parking capacity is full during week-days;
identify whether observed mobility patterns of a vehicle parking in the area comprise commuter parking patterns;
Identify, based on map data, a location of a public transportation stop within a predetermined range of the area;
determine, based on historical traffic data and real-time traffic data, whether an observed traffic congestion increases from a historical traffic congestion level for observed traffic from the public transportation stop to a city center;
determine whether a full on-street parking capacity and/or a full off-street parking capacity during the day negatively modifies a mobility pattern of a resident of the area; and
determine, based on at least one of the observed mobility pattern of the vehicle parking in the area, the observed traffic congestion and the mobility pattern of the resident of the area, a current virtual park and ride index, where the current virtual park and ride index comprises a likelihood of the vehicle parking at a current virtual park and ride hub;
hub;
update a database with a recommended virtual park and ride hub based on the future virtual park and ride index, map data, the real-time traffic data, public transportation data; and
activate an autonomous vehicle control system in response to the recommended virtual park and ride hub.
9 . The system of claim 8 , further comprising computer executable instructions to determine, using a trained machine learning model based on the current virtual park and ride index and area map features, a future virtual park and ride index, where the future virtual park and ride index comprises a likelihood of the vehicle parking at a future virtual park and ride hub.
10 . The system of claim 9 , further comprising computer executable instructions to provide, to a user, a recommended virtual park and ride hub based on the future virtual park and ride index, map data, the real-time traffic data, public transportation data, user travel preferences and/or user mobility patterns.
11 . The system of claim 10 , further comprising computer executable instructions to provide, based on the recommended virtual park and ride hub, suggestions to: park the vehicle at a different public transportation stop to reduce traffic congestion; choose a different virtual park and ride route to reduce an impact on the mobility pattern of the resident of the area; and/or recommend car-pooling from a start area to the recommended virtual park and ride hub based on similar mobility patterns of other commuters.
12 . The system of claim 10 , further comprising computer executable instructions to suggest a virtual electric vehicle charging point park and ride hub that allows electric vehicles to charge within a predetermined location from the public transportation stop.
13 . The system of claim 8 , where the commuter parking patterns are determined from video data collected by cameras positioned in the area.
14 . The system of claim 10 , where the computer executable instructions to provide, to the user, the recommended virtual park and ride hub comprise computer executable instructions to provide, to the user, the recommended virtual park and ride hub on a visual display.